Inside your boundary
Local keeps authority.
Merlin can use a local inference fleet while the runtime governs tools, workspace changes and final answers. Model routing and permission to act are separate responsibilities.
03 / Run it yourself
Control where the work runs.
Your infrastructure. Your model choices. An explicit boundary for anything that leaves it.
At the boundary
Cloud is a configuration choice.
Cloud escalation exists for long context and other configured routing policies. It can be switched off. If enabled, requests sent to those providers can carry context; review the actual profile before treating a workload as local-only.
Deployment considerations
Choose the workload before the hardware.
Model size, quantization, context length and simultaneous requests all affect capacity. A diagram with three accelerator symbols is not a three-GPU requirement, and there is no single memory figure that fits every deployment.
Before a first run
Make these decisions explicit.
Which models may receive the workload? Which sources and tools may it access? Which provider fallbacks are enabled? What evidence is required before changes and completion?
From the lab
The machines behind the work.
The fleet deserves to be shown as it is. The photograph is still to be captured; the architecture above is a conceptual drawing.
Rig photograph — the actual fleet host and accelerators. Awaiting photography.